Chargement...
 

Historique de fiche de formulaire


Version Date Utilisateur ID du Champ Champ Difference
1 180 Abstract
-This work aims for the recognition of actions, gestures and complex activities by artificial vision. From the analysis of optical flow, elementary events will be characterized. Spatio-temporal relationships of these elementary events will be modeled in a compact and discriminative way in order to represent more complex activities. In particular, the PhD will focus on the covariance region descriptors for merging visual information of heterogeneous natures (optical flow, depth, color and texture). The representation of complex actions will be applied to urban surveillance and human-computer interaction. +This work aims to propose a unified method for region tracking and motion recognition, that could be applied on 2D or 3D data depending on the context. First, low-level features will be extracted from optical flow analysis to characterize key elementary events. Spatio-temporal relationships of these elementary events will be modeled in a compact and discriminative way in order to represent more complex activities. In particular, the PhD will focus on the covariance region descriptors for merging visual information of heterogeneous natures (optical flow, depth, color and texture). The representation of complex actions will be applied to urban surveillance and human-computer interaction.
      181 Context
-Automatically recognizing an action, a gesture, an activity in a video is a major issue in computer vision, for automatic video surveillance, human-computer interaction or indexing databases videos. For over ten years, many approaches have been introduced but a reliable application in real conditions remains a challenging. To demonstrate the generic nature of the proposed approach and study two different scales, two applications will be covered: +Automatically recognizing an action, a gesture, an activity in a video is a major issue in computer vision, for automatic video surveillance, human-computer interaction or videos indexing. For over ten years, many approaches have been introduced but a reliable application in real conditions remains challenging. To demonstrate the generic nature of the proposed approach and study two different scales, two applications will be covered:
 (1) video surveillance : the aim is to identify and automatically save events and activities visible in a video and detect any abnormal events. It is a difficult problem because of the diversity of events, the variability in appearance and also the diversity of the meaning of the concept of abnormality. (1) video surveillance : the aim is to identify and automatically save events and activities visible in a video and detect any abnormal events. It is a difficult problem because of the diversity of events, the variability in appearance and also the diversity of the meaning of the concept of abnormality.
 (2) human-machine interaction: simple actions (selection, moving a message, change viewing options, zoom, scroll) to complex (eg a gesture for a shortcut to a application, writing, elements of sign language) (2) human-machine interaction: simple actions (selection, moving a message, change viewing options, zoom, scroll) to complex (eg a gesture for a shortcut to a application, writing, elements of sign language)
      182 Work program
-- State of the art review: covariance descriptors for complex activity recognition (actions and gestures).- Developments- Implementation of an application of human activities classification in complex scenes.- Evaluation of the results on public database - Publication- Implementation of an application of gesture classification in complex scenes.- Evaluation of the results on public database - Publication- Writing of the PhD manuscript +1- Bibliographic review on covariance descriptors for complex activity recognition (actions and gestures).2- Proposition of a first methodology on 2D motion characterization.Application to human activities classification in complex scenes, evaluation of the results on public database and publication3- Proposition of a second methodology on 3D motion characterization for gesture analysis. Application to gesture classification in complex scenes, evaluation of the results on public database and publication4- Towards a unified approach of tracking and recognition5- PhD manuscript and defence
-The project should lead to the development of an innovative approach to a conceptual and methodological perspective. It should allow for clear conclusions regarding the strengths and weaknesses of covariance descriptors for action recognition. +The expected results are clear conclusions regarding the strengths and weaknesses of covariance descriptors for action recognition.
      183 Objectives
-The objective is to develop new methods for motion description and recognition based on covariance descriptors [Tuzel06] for human computer interaction and videosurveillance. These methods have been mainly applied to object recognition and tracking and are of growing interest [ Lui12 ], since regions are represented by a discriminant and compact matrix (of fixed size regardless of the resolution of the object, typically 7x7) which mixes visual features of heterogeneous types. Each pixel of the object is represented by a feature vector consisting of geometric ( spatial coordinates , gradient, texture ) , radiometric or kinematic descriptors. In the case of actions identification, existing methods [Guo10, Guo11, Sanin13] using a covariance descriptor are quite promising. +The objective is to develop new methods for motion description and recognition based on covariance descriptors [Tuzel06] for human computer interaction and videosurveillance. These methods have been mainly applied to object recognition and tracking and are of growing interest [ Lui12 ], since regions are represented by a discriminant and compact matrix (of fixed size regardless of the resolution of the object, typically 7x7) which mixes visual features of heterogeneous types. Each pixel of the object is represented by a feature vector consisting of geometric ( spatial coordinates , gradient, texture ) , radiometric or kinematic descriptors. In the case of actions identification, existing methods [Guo10, Guo11, Sanin13] using a covariance descriptor are quite promising. The objective is to extend the extend the existing method to 3D motion, to propose a unified tracking/recognition technique.
      188 Co-advisors
- +Samia Bouchafa
      189 Collaborations
- +IBISC Evry

Ecole Doctorale Informatique Paris-Sud


Directrice
Nicole Bidoit
Assistante
Stéphanie Druetta
Conseiller aux thèses
Dominique Gouyou-Beauchamps

ED 427 - Université Paris-Sud
UFR Sciences Orsay
Bat 650 - aile nord - 417
Tel : 01 69 15 63 19
Fax : 01 69 15 63 87
courriel: ed-info à lri.fr